electra-base-discriminator-jailbreakv-28k-augmented
This model is a fine-tuned version of google/electra-base-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0051
- Accuracy: 0.9982
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0637 | 1.0 | 7840 | 0.0127 | 0.9958 |
| 0.0001 | 2.0 | 15680 | 0.0120 | 0.9968 |
| 0.0156 | 3.0 | 23520 | 0.0083 | 0.9976 |
| 0.0122 | 4.0 | 31360 | 0.0051 | 0.9982 |
| 0.0058 | 5.0 | 39200 | 0.0053 | 0.9983 |
| 0.0240 | 6.0 | 47040 | 0.0075 | 0.9981 |
| 0.0059 | 7.0 | 54880 | 0.0108 | 0.9975 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2